Model Details
Released
Jan 21, 2025
Where is Sonar a perfect fit?
Sonar is designed for search-integrated AI workflows, combining retrieval with generation for up-to-date answers. Ideal for:
- AI-powered search engines and answer engines
- Retrieval-augmented generation (RAG) with live web data
- Research assistants requiring real-time information
- Knowledge discovery and summarisation across sources
- Applications needing citations and grounded responses
- Workflows where freshness of data matters more than static knowledge
- AI-powered search engines and answer engines
- Retrieval-augmented generation (RAG) with live web data
- Research assistants requiring real-time information
- Knowledge discovery and summarisation across sources
- Applications needing citations and grounded responses
- Workflows where freshness of data matters more than static knowledge
Quick Model Estimate
Your Sonar Cost Estimate
💰 Total Cost
—
for 1000 input + 1000 output tokens
📥 Input (1000 × $1.000000)
—
📤 Output (1000 × $1.000000)
—
Cost Breakdown
📥 Input
📤 Output
Prices are watched for changes and checked against the provider's own page.
Pricing
|
Provider
↕
|
Modality
↕
|
Service Tier
↕
|
Input Price
(per 1M tokens) ↕ |
Output Price
(per 1M tokens) ↕ |
Context Size
↕
|
View
|
|---|---|---|---|---|---|---|
 Perplexity | Text | Standard | $1.0000 | $1.0000 | N/A | → |
Other Models in the Sonar Family
FAQs about Sonar
How much does Sonar cost per 1M tokens?
Sonar costs $1.00 per million input tokens, and $1.00 per million output tokens.
What does a typical workload cost with Sonar?
1,000 requests of 2,000 input and 500 output tokens each — 2,000,000 input and 500,000 output tokens in total — costs $2.50 with Sonar at its lowest rates. Use the calculator on this page for your own volumes.
Where can I use Sonar?
Sonar is available through Perplexity, from $1.00 per million input tokens.